• University of Bristol Featured PhD Programmes
  • University of Leeds Featured PhD Programmes
  • University of Cambridge Featured PhD Programmes
  • London School of Economics and Political Science Featured PhD Programmes
  • University of Mannheim Featured PhD Programmes
  • University of Glasgow Featured PhD Programmes
  • Carlos III Health Institute Featured PhD Programmes
  • University of Leeds Featured PhD Programmes
Wellcome Trust Featured PhD Programmes
Imperial College London Featured PhD Programmes
University of Bristol Featured PhD Programmes
University of Warwick Featured PhD Programmes
University of Bristol Featured PhD Programmes

An Argumentation Workbench

This project is no longer listed in the FindAPhD
database and may not be available.

Click here to search the FindAPhD database
for PhD studentship opportunities
  • Full or part time
    Dr Wyner
    Dr Van Deemter
  • Application Deadline
    Applications accepted all year round

Project Description

Individuals, companies, and government organisations rely on textual information found on the Internet to help to make decisions about plans and actions. However, the information often appears in high volume, in a variety of formats, distributed over entries, represented in language, and largely unstructured. While a consumer of the information might read a few entries, it is very difficult for her to gain a coherent understanding of arguments about the topic from across a corpus, where arguments are justifications for a conclusion. There is too much complex information. What a user wants is an analysis of the argument served on a web-based interface, where the user can trace the reasoning from premises to conclusion and interact by answering structured questions. Thus, a user would have a clear summary of the elements and structure of the argument, rather than trying to manually reconstruct it from distributed textual information. However, to provide such an analysis, we need to develop workbench tools to support extraction and reconstruction of textual material.

The PhD project will contribute to research on semi-automatic tools to construct coherent, well-structured arguments derived from the source text. The research will address several main challenges in a processing pipeline, each of which present significant areas for scientific development, such as the following. What argumentation schemes are needed? How can we use text analytic components to annotate and extract relevant information? What sorts of normalisation/summarisation of the text is needed? How can we identify exceptions and contrastive meaning. The results of the research will have very broad application and deep impact.

The outcome of the project will be evaluated in terms of both performance and quality with comparisons to state-of-the-art systems.

During the project, student will also be supervised on the methodology of scientific research, experimenting, writing, presenting, team-working.

The successful applicant should have, or expect to have, an Honours Degree at 2.1 or above (or equivalent) in Computer Science. It is essential for student to have solid knowledge about one of the following disciplines of modern computer science and artificial intelligence: discrete mathematics, computational linguistics, knowledge-based systems, machine learning. It is important for the student to have basic understanding of modern database systems and distributed systems. The student should have good programming skills.

Funding Notes

There is no funding attached to this project, it is for self-funded students only.

References

Application Process:

Formal applications can be completed online: http://www.abdn.ac.uk/postgraduate/apply. You should apply for PhD in Computing Science, to ensure that your application is passed to the correct College for processing. Please ensure that you quote the project title and supervisor on the application form.

Informal inquiries can be made to Dr A Wyner ([email protected]) with a copy of your curriculum vitae and cover letter. All general enquiries should be directed to the Graduate School Admissions Unit ([email protected]).

Share this page:

Cookie Policy    X